Deep Subdomain Adaptation Network for Image Classification

Abstract

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to Subdomain Adaptation which focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods which contain several loss functions and converge slowly. Based on this, we present Deep Subdomain Adaptation Network (DSAN) which learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at: https://github.com/easezyc/deep-transfer-learning

arXiv commentpublished on TNNLS

References in corpus (13)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• VisDA: The Visual Domain Adaptation Challenge
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
• Multi-Representation Adaptation Network for Cross-domain Image Classification
• A Comprehensive Survey on Transfer Learning
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Co-regularized Alignment for Unsupervised Domain Adaptation

Cited by in corpus (35)

• A Survey on Negative Transfer
• Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification
• Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
• Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning
• ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data
• On The Effects Of Data Normalisation For Domain Adaptation On EEG Data
• Cross-domain Activity Recognition via Substructural Optimal Transport
• Contrastive Domain Adaptation for Time-Series via Temporal Mixup
• AdaRNN: Adaptive Learning and Forecasting of Time Series
• Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification
• Unsupervised Domain Adaption Harnessing Vision-Language Pre-training
• Towards Unsupervised Domain Adaptation via Domain-Transformer
• Improving Domain Adaptation Through Class Aware Frequency Transformation
• Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification
• Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
• Multi-Objective Meta Learning
• Domain Adaptation Techniques for Natural and Medical Image Classification
• BiPC: Bidirectional Probability Calibration for Unsupervised Domain Adaption
• Knowledge Distillation and Enhanced Subdomain Adaptation Using Graph Convolutional Network for Resource-Constrained Bearing Fault Diagnosis
• Consistent Assistant Domains Transformer for Source-free Domain Adaptation
• OmniPrint: A Configurable Printed Character Synthesizer
• Unsupervised domain adaptation via double classifiers based on high confidence pseudo label
• Bridging Simulation and Experiment: A Self-Supervised Domain Adaptation Framework for Concrete Damage Classification
• KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment
• DRR4Covid: Learning Automated COVID-19 Infection Segmentation from Digitally Reconstructed Radiographs
• Conditional Bures Metric for Domain Adaptation
• Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency
• Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization
• Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
• Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration
• Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching